{"id":"https://openalex.org/W2127172428","doi":"https://doi.org/10.1109/icassp.2008.4518685","title":"Segment selection method based on tonal validity evaluation using machine learning for concatenative speech synthesis","display_name":"Segment selection method based on tonal validity evaluation using machine learning for concatenative speech synthesis","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2127172428","doi":"https://doi.org/10.1109/icassp.2008.4518685","mag":"2127172428"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518685","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030118011","display_name":"Akihiro Yoshida","orcid":"https://orcid.org/0000-0002-0573-5298"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Yoshida","raw_affiliation_strings":["NTT Cyber Space Laboratories, NTT Corporation, Yokosuka, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Cyber Space Laboratories, NTT Corporation, Yokosuka, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021823131","display_name":"Hideyuki Mizuno","orcid":"https://orcid.org/0000-0002-2866-7400"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki Mizuno","raw_affiliation_strings":["NTT Cyber Space Laboratories, NTT Corporation, Yokosuka, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Cyber Space Laboratories, NTT Corporation, Yokosuka, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082062172","display_name":"Kazunori Mano","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Mano","raw_affiliation_strings":["NTT Cyber Space Laboratories, NTT Corporation, Yokosuka, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Cyber Space Laboratories, NTT Corporation, Yokosuka, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3872,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57741509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4617","last_page":"4620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613595724105835},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7215523719787598},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7013698220252991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6855598092079163},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6092907786369324},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5943723917007446},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5818273425102234},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.5754545331001282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5726718902587891},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5603191256523132},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5145723223686218},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45750004053115845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1507718861103058},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.13255411386489868},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1014946699142456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613595724105835},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7215523719787598},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7013698220252991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6855598092079163},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6092907786369324},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5943723917007446},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5818273425102234},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.5754545331001282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726718902587891},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5603191256523132},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5145723223686218},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45750004053115845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1507718861103058},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.13255411386489868},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1014946699142456},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518685","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W60527148","https://openalex.org/W160640889","https://openalex.org/W2116661712","https://openalex.org/W2146043470","https://openalex.org/W2150658333","https://openalex.org/W2156909104","https://openalex.org/W2394921947","https://openalex.org/W2598876254","https://openalex.org/W6602498108","https://openalex.org/W6681329805","https://openalex.org/W6712208827","https://openalex.org/W6735227744"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W234770729","https://openalex.org/W4298046075","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W4379055549","https://openalex.org/W2387179309"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,58],"speech":[4,14,50,155],"segment":[5,65,137],"selection":[6,138],"method":[7,19,150,163],"based":[8,66],"on":[9,67],"machine":[10,31],"learning":[11],"for":[12,120],"concatenative":[13],"synthesis":[15],"systems.":[16],"The":[17,52,70,93,144],"proposed":[18,136,149],"has":[20],"two":[21,74],"novel":[22],"features.":[23],"One":[24],"is":[25,54,98,128],"its":[26,55,126],"use":[27,56],"of":[28,38,47,57,80,83,95,134],"support":[29],"vector":[30],"(SVM)":[32],"to":[33,43,61,101],"estimate":[34],"the":[35,63,78,87,90,106,132,135,148,161],"subjective":[36],"correctness":[37],"pitch":[39],"accent":[40,45,122],"with":[41,156],"respect":[42],"each":[44,81],"phrase":[46],"possible":[48],"candidate":[49],"segments.":[51],"other":[53,88],"determination":[59,71],"function":[60,72],"identify":[62],"best":[64],"SVM":[68,84,96,108,118],"output.":[69],"involves":[73],"assessments;":[75],"one":[76],"counts":[77],"number":[79],"sign":[82,94],"output":[85,97,109],"and":[86,169],"compares":[89],"distance":[91,107],"values.":[92],"generally":[99],"used":[100],"classify":[102],"target":[103,167],"objects,":[104],"but":[105],"also":[110],"represents":[111],"important":[112],"information.":[113],"An":[114],"experiment":[115],"that":[116,125,147,164],"assesses":[117],"performance":[119],"Japanese":[121,153],"validity":[123],"shows":[124],"accuracy":[127],"81%.":[129],"To":[130],"confirm":[131],"effectiveness":[133],"method,":[139],"preference":[140],"tests":[141],"are":[142],"conducted.":[143],"test":[145],"indicates":[146],"can":[151],"yield":[152],"synthesized":[154],"more":[157],"natural":[158],"intonation":[159],"than":[160],"conventional":[162],"uses":[165],"only":[166],"cost":[168],"concatenation":[170],"cost.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}